© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 2-MLP
    11. 4730
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    list item containing string (negative activations)

    python-code · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quired
    -0.06
    _dep
    -0.05
    umn
    -0.05
     task
    -0.05
     tasks
    -0.05
    _tasks
    -0.05
     robot
    -0.05
     depth
    -0.05
     dep
    -0.05
    split
    -0.04
    POSITIVE LOGITS
    (self
    0.11
     self
    0.09
     other
    0.08
    self
    0.08
    __(
    0.07
    param
    0.07
    other
    0.06
    args
    0.06
    par
    0.06
    č
    0.05
    Activations Density 91.058%

    No Known Activations